Interpretable machine learning analysis of immune-inflammatory biomarkers for predicting no-reflow in patients with acute myocardial infarction after percutaneous coronary intervention.
6 affiliations
- 1Department of Cardiovascular Medicine, Southwest Hospital, Army Medical University, Chongqing, China.
- 2Key Laboratory of Geriatric Cardiovascular and Cerebrovascular Disease, Ministry of Education of China, Chongqing, China.
- 3Key Laboratory of Chronobiology and Cardiometabolic Disease, Chongqing Education Commission of China, Chongqing, China.
- 4Center for Medical Big Data and Artificial Intelligence, Southwest Hospital, Army Medical University, Chongqing, China.
- 5Medical Team, Xiangyang Detachment of the Armed Police Force, Hubei, China.
- 6School of Medicine, Chongqing University, Chongqing, China.
Abstract
Objective
To evaluate whether routine immune-inflammatory biomarkers predict no-reflow (NR) after percutaneous coronary intervention (PCI) in acute myocardial infarction (AMI) patients, quantify their incremental predictive value over clinical variables, and build an interpretable peri-procedural prediction model.Methods
This prospective cohort recruited 382 AMI patients undergoing PCI. Univariable and multivariable logistic regression identified independent correlates; confounder-adjusted restricted cubic splines (RCS) assessed nonlinear associations. LASSO regression selected core predictors with variance inflation factor (VIF) assessing multicollinearity. Four machine-learning models underwent 1000-iteration bootstrap internal validation and SHAP interpretation. Incremental value was tested via ΔAUC (DeLong test), continuous NRI, and IDI. Stratified regression and interaction tests evaluated AMI-subtype effect modification.Results
NR occurred in 91 patients (23.8%). Multiple neutrophil-centred indices independently correlated with NR after adjustment. Seven predictors constituted the final model (all VIF < 2.5). LightGBM yielded optimal discrimination and modest net clinical benefit (AUC 0.799, 95% CI 0.699-0.899); AMI subtype and neutrophil-related markers dominated SHAP outputs. Neutrophil count, NAR, NHR, SII, and PIV significantly improved discrimination. Seven of the 16 tested markers yielded significant continuous NRI, and ten demonstrated significant IDI gains. In stratified analyses, neutrophil count, NLR, and MHR were associated with NR in STEMI but not NSTEMI patients; interaction tests found no significant AMI-subtype effect modification.Conclusion
Pre-procedural neutrophil-centred inflammatory biomarkers are independent correlates of post-PCI NR and offer incremental predictive value over conventional clinical variables. The interpretable LightGBM model supports peri-procedural NR risk stratification, though external validation and recalibration are mandatory before clinical application.
Related
- A machine learning model for predicting ischemic and bleeding risk after percutaneous coronary intervention: Development and external validation
- Nomogram for predicting post-percutaneous coronary intervention restenosis in patients with coronary artery disease and diabetes: a retrospective study
- Interpretable Machine Learning Prognostic Model Integrating Inflammatory-Nutritional Biomarkers for Post-Prostatectomy Biochemical Recurrence: Development, Internal Validation, and Translational Target Exploration.
- Effects of Blueberry and Collard Greens Dietary Intervention on Metabolic and Inflammatory Biomarkers in Zucker Obese Rats
- Blood-based biomarkers and major adverse cardiac events after percutaneous coronary intervention: a systematic review with narrative synthesis
BibTeX
@article{liu2026interpretable,
title = {{Interpretable machine learning analysis of immune-inflammatory biomarkers for predicting no-reflow in patients with acute myocardial infarction after percutaneous coronary intervention.}},
author = {Rensong Liu and Yan Peng and Haoran Qin and Yang Zhou and Xiaolong Li and Hongqian Wang and Ying Li and Hanlin Zhang and Xinyi Hu and Zhouqing Zhang and Weiran Ren and Xianlong Shu and Junhao Zhang and Li Nie and Xinliang Zou and Tao Jing},
journal = {Annals of medicine},
year = {2026},
month = oct,
doi = {10.1080/07853890.2026.2747562},
url = {https://europepmc.org/article/MED/42886571},
note = {CC BY},
}
RIS
TY - JOUR
TI - Interpretable machine learning analysis of immune-inflammatory biomarkers for predicting no-reflow in patients with acute myocardial infarction after percutaneous coronary intervention.
AU - Rensong Liu
AU - Yan Peng
AU - Haoran Qin
AU - Yang Zhou
AU - Xiaolong Li
AU - Hongqian Wang
AU - Ying Li
AU - Hanlin Zhang
AU - Xinyi Hu
AU - Zhouqing Zhang
AU - Weiran Ren
AU - Xianlong Shu
AU - Junhao Zhang
AU - Li Nie
AU - Xinliang Zou
AU - Tao Jing
PY - 2026
DA - 2026/10/16
JO - Annals of medicine
DO - 10.1080/07853890.2026.2747562
UR - https://europepmc.org/article/MED/42886571
AB - Objective To evaluate whether routine immune-inflammatory biomarkers predict no-reflow (NR) after percutaneous coronary intervention (PCI) in acute myocardial infarction (AMI) patients, quantify their incremental predictive value over clinical variables, and build an interpretable peri-procedural prediction model.Methods This prospective cohort recruited 382 AMI patients undergoing PCI. Univariable and multivariable logistic regression identified independent correlates; confounder-adjusted restricted cubic splines (RCS) assessed nonlinear associations. LASSO regression selected core predictors with variance inflation factor (VIF) assessing multicollinearity. Four machine-learning models underwent 1000-iteration bootstrap internal validation and SHAP interpretation. Incremental value was tested via ΔAUC (DeLong test), continuous NRI, and IDI. Stratified regression and interaction tests evaluated AMI-subtype effect modification.Results NR occurred in 91 patients (23.8%). Multiple neutrophil-centred indices independently correlated with NR after adjustment. Seven predictors constituted the final model (all VIF < 2.5). LightGBM yielded optimal discrimination and modest net clinical benefit (AUC 0.799, 95% CI 0.699-0.899); AMI subtype and neutrophil-related markers dominated SHAP outputs. Neutrophil count, NAR, NHR, SII, and PIV significantly improved discrimination. Seven of the 16 tested markers yielded significant continuous NRI, and ten demonstrated significant IDI gains. In stratified analyses, neutrophil count, NLR, and MHR were associated with NR in STEMI but not NSTEMI patients; interaction tests found no significant AMI-subtype effect modification.Conclusion Pre-procedural neutrophil-centred inflammatory biomarkers are independent correlates of post-PCI NR and offer incremental predictive value over conventional clinical variables. The interpretable LightGBM model supports peri-procedural NR risk stratification, though external validation and recalibration are mandatory before clinical application.
SN - 0785-3890
SN - 1365-2060
ER -